{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XD746KBWN7PM77OWZDFMD6TYZ4","short_pith_number":"pith:XD746KBW","schema_version":"1.0","canonical_sha256":"b8ffcf28366fdecffdd6c8cac1fa78cf0c1ce30982b45f6153becb3f4b1fac8d","source":{"kind":"arxiv","id":"2201.10222","version":1},"attestation_state":"computed","paper":{"title":"Explanatory Learning: Beyond Empiricism in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","physics.hist-ph"],"primary_cat":"cs.LG","authors_text":"Andrea Santilli, Antonio Norelli, Emanuele Rodol\\`a, Giambattista Parascandolo, Giorgio Mariani, Luca Moschella, Simone Melzi","submitted_at":"2022-01-25T10:21:53Z","abstract_excerpt":"We introduce Explanatory Learning (EL), a framework to let machines use existing knowledge buried in symbolic sequences -- e.g. explanations written in hieroglyphic -- by autonomously learning to interpret them. In EL, the burden of interpreting symbols is not left to humans or rigid human-coded compilers, as done in Program Synthesis. Rather, EL calls for a learned interpreter, built upon a limited collection of symbolic sequences paired with observations of several phenomena. This interpreter can be used to make predictions on a novel phenomenon given its explanation, and even to find that e"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2201.10222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-25T10:21:53Z","cross_cats_sorted":["cs.AI","cs.CL","physics.hist-ph"],"title_canon_sha256":"c8666d109c6181c7c72628817f76a55d4a6006ade17cf0485d759929a8b5d1f8","abstract_canon_sha256":"deba67ced515fcb43810b2c2867329afe7177fd8ae6477e72ffe6ea652750f5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:16.878906Z","signature_b64":"1P9wV1fevVbfKlkhtx85eIgHA0O6NZuI3fTyh+a2bXByC0LETVDYmObgN3IHr8eHQE0QUnwbmD3yoik9PF5IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8ffcf28366fdecffdd6c8cac1fa78cf0c1ce30982b45f6153becb3f4b1fac8d","last_reissued_at":"2026-07-05T03:51:16.878505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:16.878505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explanatory Learning: Beyond Empiricism in Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","physics.hist-ph"],"primary_cat":"cs.LG","authors_text":"Andrea Santilli, Antonio Norelli, Emanuele Rodol\\`a, Giambattista Parascandolo, Giorgio Mariani, Luca Moschella, Simone Melzi","submitted_at":"2022-01-25T10:21:53Z","abstract_excerpt":"We introduce Explanatory Learning (EL), a framework to let machines use existing knowledge buried in symbolic sequences -- e.g. explanations written in hieroglyphic -- by autonomously learning to interpret them. In EL, the burden of interpreting symbols is not left to humans or rigid human-coded compilers, as done in Program Synthesis. Rather, EL calls for a learned interpreter, built upon a limited collection of symbolic sequences paired with observations of several phenomena. This interpreter can be used to make predictions on a novel phenomenon given its explanation, and even to find that e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10222","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2201.10222/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2201.10222","created_at":"2026-07-05T03:51:16.878559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.10222v1","created_at":"2026-07-05T03:51:16.878559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10222","created_at":"2026-07-05T03:51:16.878559+00:00"},{"alias_kind":"pith_short_12","alias_value":"XD746KBWN7PM","created_at":"2026-07-05T03:51:16.878559+00:00"},{"alias_kind":"pith_short_16","alias_value":"XD746KBWN7PM77OW","created_at":"2026-07-05T03:51:16.878559+00:00"},{"alias_kind":"pith_short_8","alias_value":"XD746KBW","created_at":"2026-07-05T03:51:16.878559+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11672","citing_title":"Artificial Scientific Discovery","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4","json":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4.json","graph_json":"https://pith.science/api/pith-number/XD746KBWN7PM77OWZDFMD6TYZ4/graph.json","events_json":"https://pith.science/api/pith-number/XD746KBWN7PM77OWZDFMD6TYZ4/events.json","paper":"https://pith.science/paper/XD746KBW"},"agent_actions":{"view_html":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4","download_json":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4.json","view_paper":"https://pith.science/paper/XD746KBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.10222&json=true","fetch_graph":"https://pith.science/api/pith-number/XD746KBWN7PM77OWZDFMD6TYZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/XD746KBWN7PM77OWZDFMD6TYZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4/action/storage_attestation","attest_author":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4/action/author_attestation","sign_citation":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4/action/citation_signature","submit_replication":"https://pith.science/pith/XD746KBWN7PM77OWZDFMD6TYZ4/action/replication_record"}},"created_at":"2026-07-05T03:51:16.878559+00:00","updated_at":"2026-07-05T03:51:16.878559+00:00"}